English
Related papers

Related papers: TS-RSR: A provably efficient approach for batch Ba…

200 papers

Bayesian optimization (BO) is a widely used iterative algorithm for optimizing black-box functions. Each iteration requires maximizing an acquisition function, such as the upper confidence bound (UCB) or a sample path from the Gaussian…

Machine Learning · Statistics 2025-06-16 Hwanwoo Kim , Chong Liu , Yuxin Chen

Bayesian optimisation (BO) algorithms have shown remarkable success in applications involving expensive black-box functions. Traditionally BO has been set as a sequential decision-making process which estimates the utility of query points…

Machine Learning · Computer Science 2022-10-25 Rafael Oliveira , Louis Tiao , Fabio Ramos

This paper develops a viable notion of learning for sampling-based algorithms that applies in broader settings than previously considered. More specifically, we model a discounted infinite-horizon MDPs with Borel state and action spaces,…

Machine Learning · Statistics 2026-04-09 Daniel Adelman , Cagla Keceli , Alba V. Olivares-Nadal

We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between…

Machine Learning · Computer Science 2021-09-14 Nadav Merlis , Shie Mannor

Bayesian optimization (BO) has become popular for sequential optimization of black-box functions. When BO is used to optimize a target function, we often have access to previous evaluations of potentially related functions. This begs the…

Machine Learning · Computer Science 2022-06-17 Zhongxiang Dai , Yizhou Chen , Haibin Yu , Bryan Kian Hsiang Low , Patrick Jaillet

Motivated by the pressing need for efficient optimization in online recommender systems, we revisit the cascading bandit model proposed by Kveton et al. (2015). While Thompson sampling (TS) algorithms have been shown to be empirically…

Machine Learning · Computer Science 2021-05-18 Zixin Zhong , Wang Chi Cheung , Vincent Y. F. Tan

Distributional shifts pose a significant challenge to achieving robustness in contemporary machine learning. To overcome this challenge, robust satisficing (RS) seeks a robust solution to an unspecified distributional shift while achieving…

Machine Learning · Computer Science 2023-08-17 Artun Saday , Yaşar Cahit Yıldırım , Cem Tekin

Bayesian optimization (BO) is a widely used iterative black-box optimization method that utilizes Gaussian process (GP) surrogate models. In practice, BO is typically terminated after a fixed evaluation budget is exhausted, which can incur…

Machine Learning · Computer Science 2026-05-22 Haowei Wang , Jingyi Wang , Qiyu Wei

Bayesian optimization is a powerful tool for optimizing an expensive-to-evaluate black-box function. In particular, the effectiveness of expected improvement (EI) has been demonstrated in a wide range of applications. However, theoretical…

Machine Learning · Statistics 2025-10-01 Shion Takeno , Yu Inatsu , Masayuki Karasuyama , Ichiro Takeuchi

Bayesian Optimization (BO) is a sample-efficient optimization algorithm widely employed across various applications. In some challenging BO tasks, input uncertainty arises due to the inevitable randomness in the optimization process, such…

Machine Learning · Computer Science 2023-11-07 Lin Yang , Junlong Lyu , Wenlong Lyu , Zhitang Chen

We consider the fixed-budget best arm identification problem with rewards following normal distributions. In this problem, the forecaster is given $K$ arms (or treatments) and $T$ time steps. The forecaster attempts to find the arm with the…

Machine Learning · Statistics 2024-04-16 Junpei Komiyama

We present Acquisition Thompson Sampling (ATS), a novel technique for batch Bayesian Optimization (BO) based on the idea of sampling multiple acquisition functions from a stochastic process. We define this process through the dependency of…

Machine Learning · Computer Science 2019-10-18 Alessandro De Palma , Celestine Mendler-Dünner , Thomas Parnell , Andreea Anghel , Haralampos Pozidis

This work focuses on Bayesian optimization (BO) under reward model uncertainty. We propose the first BO algorithm that achieves no-regret guarantee in a general reward setting, requiring only Lipschitz continuity of the objective function…

Machine Learning · Computer Science 2026-02-10 Zishi Zhang , Tao Ren , Yijie Peng

Thompson sampling (TS) is a simple, effective stochastic policy in Bayesian decision making. It samples the posterior belief about the reward profile and optimizes the sample to obtain a candidate decision. In continuous optimization, the…

Machine Learning · Computer Science 2024-10-11 Taiwo A. Adebiyi , Bach Do , Ruda Zhang

In this paper, we address the challenge of sampling in scenarios where limited resources prevent exhaustive measurement across all subjects. We consider a setting where samples are drawn from multiple groups, each following a distribution…

Econometrics · Economics 2024-08-29 Carol Liu

The literature on bandit learning and regret analysis has focused on contexts where the goal is to converge on an optimal action in a manner that limits exploration costs. One shortcoming imposed by this orientation is that it does not…

Machine Learning · Computer Science 2017-05-01 Daniel Russo , David Tse , Benjamin Van Roy

Many real-world experimental design problems (a) evaluate multiple experimental conditions in parallel and (b) replicate each condition multiple times due to large and heteroscedastic observation noise. Given a fixed total budget, this…

Thompson sampling is one of the most widely used algorithms for many online decision problems, due to its simplicity in implementation and superior empirical performance over other state-of-the-art methods. Despite its popularity and…

Machine Learning · Computer Science 2020-10-02 Tianyuan Jin , Pan Xu , Jieming Shi , Xiaokui Xiao , Quanquan Gu

This paper studies regret minimization with randomized value functions in reinforcement learning. In tabular finite-horizon Markov Decision Processes, we introduce a clipping variant of one classical Thompson Sampling (TS)-like algorithm,…

Machine Learning · Computer Science 2021-11-10 Priyank Agrawal , Jinglin Chen , Nan Jiang

Most bandit algorithm designs are purely theoretical. Therefore, they have strong regret guarantees, but also are often too conservative in practice. In this work, we pioneer the idea of algorithm design by minimizing the empirical Bayes…

Machine Learning · Computer Science 2020-06-12 Chih-Wei Hsu , Branislav Kveton , Ofer Meshi , Martin Mladenov , Csaba Szepesvari